© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5471
    Prev
    Next
    INDEX
    Explanations

    comparative terms indicating improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skosten
    -0.78
    Koz
    -0.76
    URLException
    -0.76
     Koz
    -0.73
    geology
    -0.72
     Kos
    -0.70
    URIComponent
    -0.69
    topus
    -0.68
    elance
    -0.68
     ComVisible
    -0.66
    POSITIVE LOGITS
    Better
    1.53
     BETTER
    1.51
    better
    1.51
     Better
    1.50
     better
    1.43
     bedre
    1.03
     besseren
    1.03
     beter
    1.02
     bessere
    0.97
    Worse
    0.96
    Activations Density 0.047%

    No Known Activations